© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22202
    Prev
    Next
    INDEX
    Explanations

    mathematical variables like x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abler
    -0.08
    èĢĮéĻį
    -0.08
    serter
    -0.08
     pula
    -0.07
    пелÑĮ
    -0.07
    atics
    -0.07
    bies
    -0.06
    åı®
    -0.06
    ظÙĬÙħ
    -0.06
    tero
    -0.06
    POSITIVE LOGITS
    çĦ¦
    0.08
    ÑĸлÑĮ
    0.07
    {x
    0.07
    hre
    0.07
    teman
    0.07
    åŃ
    0.07
    ê¹
    0.07
     x
    0.07
     estr
    0.06
    .x
    0.06
    Activations Density 0.047%

    No Known Activations